Impact test spectrum pattern determination method and device, electronic equipment and storage medium

Abstract

The invention provides a method and device for determining an impact test spectrum pattern, electronic equipment and a storage medium. The method comprises the following steps: acquiring impact system structure data corresponding to a plurality of preset frequencies; and for the impact test data corresponding to each predetermined frequency, inputting the impact system structure data to a predetermined target prediction model, and outputting a target impact acceleration corresponding to the impact system structure data through the target prediction model, screening in a plurality of pre-constructed prediction models to obtain the target prediction model; and generating a frequency-impact acceleration atlas based on the plurality of predetermined frequencies and the target impact acceleration corresponding to the impact system structure data of the plurality of predetermined frequencies, thereby solving the technical problem of low efficiency of determining the impact test spectrum pattern in the prior art, and improving the accuracy of determining the impact test spectrum pattern.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, electronic device and storage medium for determining an impact test spectrum. Background Art

[0002] When the pyrotechnic device of a spacecraft is in operation, it will generate an explosive shock environment containing a large number of high-frequency components. Laboratory shock tests generally simulate the impact of the shock environment on the product. The shock response spectrum describes the shock by the effect of the shock load on the structural system. The shock test spectrum is mainly obtained by obtaining data through shock tests and plotting the data. As the shock magnitude increases, the debugging of the shock test spectrum is very difficult, requiring a lot of manpower and material resources, and the spectrum debugging efficiency is low. Summary of the invention

[0003] In view of this, the purpose of the present application is to propose a method, device, electronic device and storage medium for determining an impact test spectrum, so as to overcome all or part of the deficiencies in the prior art.

[0004] Based on the above-mentioned purpose, the present application provides a method for determining an impact test spectrum, including: obtaining impact system structure data corresponding to multiple predetermined frequencies; for each impact system structure data corresponding to a predetermined frequency, inputting the impact system structure data into a predetermined target prediction model, and outputting a target impact acceleration corresponding to the impact system structure data through the target prediction model, wherein the target prediction model is obtained by screening among multiple pre-built prediction models; and generating a frequency-shock acceleration graph based on the multiple predetermined frequencies and the target impact accelerations corresponding to the impact system structure data of the multiple predetermined frequencies.

[0005] Optionally, the target prediction model is obtained by screening among multiple pre-built prediction models, including: obtaining the historical impact system structure data corresponding to the multiple predetermined frequencies and the standard impact acceleration corresponding to each historical impact system structure data; for each prediction model, based on the historical impact system structure data corresponding to each predetermined frequency, determining the historical impact acceleration corresponding to each historical impact system structure data through the prediction model; based on the standard impact acceleration and historical impact acceleration corresponding to each historical impact system structure data corresponding to each prediction model, determining the target prediction model among multiple prediction models.

[0006] Optionally, the target prediction model is determined among the multiple prediction models based on the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data corresponding to each prediction model, including: for each prediction model, determining the error value of the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data, and determining the total error of the prediction model based on the error values ​​corresponding to multiple historical impact system structure data; and among the multiple prediction models, determining the prediction model corresponding to the minimum total error as the target prediction model.

[0007] Optionally, determining the error value between the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data includes: for each historical impact system structure data, calculating the absolute value of the difference between the standard impact acceleration and the historical impact acceleration, and determining the absolute value of the difference as the error value.

[0008] Optionally, determining the total error of the prediction model based on error values ​​corresponding to multiple historical impact system structure data includes: calculating a sum of multiple error values, and determining the sum as the total error.

[0009] Optionally, before inputting the shock system structure data corresponding to each predetermined frequency into a predetermined target prediction model, the method includes: preprocessing the shock system structure data.

[0010] Optionally, the preprocessing includes missing value supplementation processing and outlier removal processing.

[0011] Based on the same inventive concept, the present application also provides a device for determining an impact test spectrum, including: an acquisition module, configured to acquire impact system structure data corresponding to multiple predetermined frequencies; an output module, configured to input the impact system structure data corresponding to each predetermined frequency into a predetermined target prediction model, and output the target impact acceleration corresponding to the impact system structure data through the target prediction model, wherein the target prediction model is obtained by screening among multiple pre-built prediction models; a generation module, configured to generate a frequency-shock acceleration spectrum based on the multiple predetermined frequencies and the target impact acceleration corresponding to the impact system structure data of the multiple predetermined frequencies.

[0012] Based on the same inventive concept, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method as described above when executing the computer program.

[0013] Based on the same inventive concept, the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the method as described above.

[0014] From the above, it can be seen that the method, device, electronic device and storage medium for determining the impact test spectrum provided by the present application include obtaining impact test data and impact system structure data corresponding to multiple predetermined frequencies. For each impact system structure data corresponding to a predetermined frequency, the impact system structure data is input into a predetermined target prediction model, and the target impact acceleration corresponding to the impact system structure data is output through the target prediction model, wherein the target prediction model is obtained by screening from multiple pre-built prediction models, thereby improving the efficiency of determining the target impact acceleration and ensuring the accuracy of determining the target impact acceleration. Based on the multiple predetermined frequencies and the target impact accelerations corresponding to the impact system structure data of the multiple predetermined frequencies, a frequency-impact acceleration spectrum is generated, and the generated frequency-impact acceleration spectrum is efficient and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A schematic diagram of a shock response spectrum test device according to an embodiment of the present application;

[0017] Figure 2 A schematic flow chart of a method for determining an impact test spectrum type according to an embodiment of the present application;

[0018] Figure 3 A schematic diagram of a display page of a virtual debugging system according to an embodiment of the present application;

[0019] Figure 4 A schematic flow chart of a method for determining an impact test spectrum type according to another embodiment of the present application;

[0020] Figure 5 A statistical diagram of the target impact acceleration of an embodiment of the present application;

[0021] Figure 6 It is a structural schematic diagram of a device for determining an impact test spectrum type according to an embodiment of the present application;

[0022] Figure 7 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0024] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0025] As mentioned in the background technology section, compared with vibration testing, the principle of shock testing determines that it can only adopt open-loop control, that is, there is only sequential action between the controller and the controlled object without reverse connection and the control is carried out in one direction. The pneumatic shock test system has a complex structure, and there are many input parameters that affect the shock spectrum. In addition, multiple parameters affect each other, making it very difficult to debug the shock test spectrum. The shock test spectrum can be generated using the shock response spectrum test device. The actual test shock system: The shock response spectrum test device is as follows: Figure 1As shown, the kinetic energy released instantly by compressed air is used to push the warhead, so that the warhead hits the response plate at a certain initial velocity, so that the test fixture installed on the response plate produces a shock response spectrum waveform that meets the target spectrum requirements. The shock response spectrum test device includes an impact power system, a basic bottom plate, a power device, an impact control system, a data acquisition system and an impact response system, wherein the impact power system includes an air source, the power device includes a gun barrel and a warhead, and the shock response system includes a response plate, a felt, a fixture, a test piece, and an impact sensor. The impact power system is connected to the power device, and the impact control system is also connected to the power device. The power device acts on the shock response system that is at a certain interval with it, and the shock response system is connected to the data acquisition system. The power device is set on the basic bottom plate; the shock control system can input and modify the shock system structure data. Based on the shock system structure data provided by the shock control system, the power device uses the gas provided by the air source in the impact power system to make the warhead in the gun barrel rush out of the gun barrel and hit the response plate in the shock response system. The data acquisition system can collect data formed by the impact in the shock response system, such as a frequency-shock acceleration spectrum. Changes in the gas source pressure, felt thickness, warhead mass, warhead position, sensor position, etc. will cause changes in the impact spectrum. At present, the debugging of the impact spectrum is generally based on the empirical model to change the system input parameters so that the impact spectrum gradually approaches the reference spectrum until the tolerance requirements are met. However, in the actual debugging process, the test personnel have a unclear understanding of the relationship between the input parameters and the impact test spectrum, which results in an increase in labor and time costs. As the impact magnitude increases, too many debugging times make it difficult to maintain the strength of the tooling structure. In actual tests, the problem of tooling strength failure during the debugging of the impact spectrum has occurred many times.

[0026] In view of this, the present application embodiment proposes a method for determining the impact test spectrum, referring to Figure 2 , including the following steps:

[0027] Step 101, obtaining impact system structure data corresponding to a plurality of predetermined frequencies.

[0028] In this step, when using the impact test system to perform an impact test, multiple impact system structure data that affect the impact test spectrum are required. The predetermined frequency can be set in advance within a predetermined range. For example, when the predetermined range is 100Hz-10000Hz, the predetermined frequency can be 100Hz, 500Hz, 1000Hz, 3000Hz, 5000Hz, 7000Hz and 10000Hz. When the predetermined frequency is determined, the impact system structure data corresponding to the multiple predetermined frequencies are determined according to actual needs, wherein the impact system structure data includes multiple impact test sub-data, and the multiple impact test sub-data include test data such as the predetermined frequency, air source pressure, felt thickness, warhead height, warhead coordinates, sensor coordinates, shot point and the distance of the sensor from each bolt.

[0029] Step 102, for each impact system structure data corresponding to a predetermined frequency, input the impact system structure data into a predetermined target prediction model, and output a target impact acceleration corresponding to the impact system structure data through the target prediction model, wherein the target prediction model is obtained by screening from a plurality of pre-built prediction models.

[0030] In this step, if the test personnel determine the target impact acceleration based on the impact system structure data corresponding to all the predetermined frequencies, it will not only lead to low efficiency in determining the target impact acceleration, but also may lead to inaccurate determination of the target impact acceleration. In order to solve the above problems, for each impact system structure data corresponding to the predetermined frequency, multiple impact test sub-data in the impact system structure data are sequentially input into a predetermined target prediction model. Among them, the target prediction model is obtained by screening from multiple pre-built prediction models, which means that the target prediction model has a relatively strong prediction ability, and then the target impact acceleration corresponding to the impact system structure data is output through the target prediction model, which improves the efficiency of determining the target impact acceleration and ensures the accuracy of determining the target impact acceleration.

[0031] The target prediction model is applied to the pre-regulation of the control parameters of the impact test spectrum test, as shown in Table 1. The various impact system structure data that affect the impact test spectrum are used as input, and the predicted target impact acceleration is used as output. The component impact test spectrum debugging model is used to establish a virtual debugging system. Based on this, the impact test spectrum debugging time is reduced.

[0032] Table 1 Input and output parameters

[0033]

[0034] Step 103 : generating a frequency-shock acceleration spectrum based on the plurality of predetermined frequencies and target shock accelerations corresponding to the shock system structure data of the plurality of predetermined frequencies.

[0035] In this step, the impact system structure data has a corresponding relationship with the predetermined frequency and the target impact acceleration, so a polynomial fitting is performed based on the predetermined frequency and the target impact acceleration to obtain a fitting curve, that is, to generate a frequency-impact acceleration spectrum. The frequency-impact acceleration spectrum is the determined impact test spectrum. Since the target impact acceleration involved in generating the frequency-impact acceleration spectrum is determined with high efficiency and accuracy, the generated frequency-impact acceleration spectrum is efficient and accurate.

[0036] It should be noted that the determined frequency-shock acceleration spectrum has the following applications: comparing the above spectrum with the standard spectrum, in response to determining that the error between the above spectrum and the standard spectrum is within a predetermined error range, using the shock system structure data corresponding to the above spectrum to perform a predetermined test, for example, when performing a predetermined test on an actual test shock system, there is no need to debug multiple test data on the actual test shock system. Using the input parameters obtained through the virtual debugging system as a reference, the actual test shock system state is changed, so that the shock test spectrum during the actual test is controlled within an acceptable tolerance range.

[0037] Applying machine learning methods to impact test spectrum tests and realizing virtual debugging of impact test spectrum solves engineering problems and has great practicality. This application uses an impact test spectrum virtual debugging system to replace the actual test impact system for spectrum debugging, which can effectively reduce the spectrum debugging time and increase the service life of the test system and the transfer tooling. Based on the established prediction model, impact test spectrum prediction software is developed and a virtual debugging system is established. In actual application, the input parameters are continuously changed in the virtual debugging system to obtain an impact test spectrum that meets the tolerance requirements, that is, the spectrum debugging is performed by replacing the actual test impact system with a virtual debugging system. Using the input parameters obtained through the virtual debugging system as a reference, the state of the actual test impact system is changed, so that the impact test spectrum during the actual test is controlled within an acceptable tolerance range. The prediction accuracy of the acceleration at each frequency point is high at a hit rate of ±30%. Therefore, when predicting the impact spectrum through the virtual debugging system, the amplitude of the predicted spectrum frequency domain acceleration is amplified by ±30%, such as Figure 3 As shown by the blue solid line in the middle, when the predicted spectrum (±30%) meets the upper and lower tolerance requirements, the impact response spectrum test system is debugged with reference to the input parameters in the virtual debugging system, and finally the test conditions that meet the tolerance requirements are obtained.

[0038] Through the above scheme, the impact system structure data corresponding to each predetermined frequency is obtained. For each impact system structure data corresponding to the predetermined frequency, the impact system structure data is input into a predetermined target prediction model, and the target impact acceleration corresponding to the impact system structure data is output through the target prediction model, wherein the target prediction model is obtained by screening from a plurality of pre-built prediction models, thereby improving the efficiency of determining the target impact acceleration and ensuring the accuracy of determining the target impact acceleration. Based on the plurality of predetermined frequencies and the target impact acceleration corresponding to the impact system structure data of the plurality of predetermined frequencies, a frequency-impact acceleration spectrum is generated, and the generated frequency-impact acceleration spectrum is efficient and accurate.

[0039] In some embodiments, the target prediction model is obtained by screening among multiple pre-built prediction models, including: obtaining the historical impact system structure data corresponding to the multiple predetermined frequencies and the standard impact acceleration corresponding to each historical impact system structure data; for each prediction model, based on the historical impact system structure data corresponding to each predetermined frequency, determining the historical impact acceleration corresponding to each historical impact system structure data through the prediction model; based on the standard impact acceleration and historical impact acceleration corresponding to each historical impact system structure data corresponding to each prediction model, determining the target prediction model among multiple prediction models.

[0040] In this embodiment, historical impact system structure data of impact test spectra corresponding to multiple predetermined frequencies and standard impact acceleration corresponding to each historical impact system structure data are obtained, wherein the standard impact acceleration is a predetermined impact acceleration with accuracy. Multiple prediction models are pre-trained. Since the impact system structure data has a large discrete feature, the machine learning algorithm that is sensitive to continuous data generally has poor performance, while the decision tree-based model may have better prediction accuracy. Therefore, the multiple prediction models can be CatBoost (categorical boosting), XGBoost (eXtreme Gradient Boosting), LightGBM (Light Gradient Boosting Machine), RF (Random Forest), DT (Decision Tree), LR (Logistic Regression) and KNN (k-Nearest Neighbor) and other machine learning algorithms. The training process for each prediction model is as follows: All experimental data sets are randomly divided into training sets and test sets at a ratio of 3:7. The data division is performed by stratified sampling to ensure the consistency of the distribution of training data and test data. The model is trained using the training set, and the model performance is evaluated using the prediction set, with the percentage error of each point as the evaluation indicator: Where δ is the percentage error, y a is the actual output value, y p is the predicted output value.

[0041] For each prediction model: for each historical impact system structure data corresponding to a predetermined frequency, the historical impact system structure data is input into the prediction model, and the best prediction result under the prediction model is obtained through continuous iterative optimization, and the historical impact acceleration corresponding to the historical impact system structure data is output through the prediction model. The historical impact system structure data input into each prediction model corresponds to the standard impact acceleration and the historical impact acceleration. Through the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data corresponding to each prediction model, the target prediction model is determined from multiple prediction models to achieve the purpose of screening the prediction model with the best prediction ability.

[0042] It should be noted that CatBoost is an open source machine learning algorithm from Yandex. It can be easily integrated with deep learning frameworks. CatBoost is a GBDT framework based on symmetric decision trees (oblivious trees) with fewer parameters, support for categorical variables and high accuracy. The main pain point it solves is to efficiently and reasonably process categorical features. CatBoost consists of Categorical and Boosting. In addition, CatBoost also solves the problems of gradient bias and prediction shift, thereby reducing the occurrence of overfitting and improving the accuracy and generalization of the algorithm. Xgboost is a distributed and efficient gradient boosting algorithm based on decision trees (CART), which can be applied to tasks such as classification, regression, and sorting. Xgboost is an improved algorithm based on CBDT, which uses multi-threaded parallelism to improve the algorithm to improve accuracy. Xgboost uses first-order and second-order derivatives to perform the second-order Taylor expansion of the loss function. LightGBM achieves efficient data processing and fast training through a histogram-based decision tree algorithm, and is widely used in machine learning tasks such as classification, regression, and ranking. RF contains multiple decision tree classifiers, and the category of its output is determined by the majority of the categories output by individual trees. RF is a flexible and easy-to-use machine learning algorithm that can get good results in most cases even without hyperparameter tuning. DT usually recursively selects the optimal feature and splits the training data according to the feature so that each sub-dataset has the best classification. This process corresponds to the division of the feature space and the construction of the decision tree. LR classifies samples by mapping the output of the linear model to between 0 and 1 using a logical function (sigmoid function). The basic idea of ​​LR is to use the weighted sum of the features of the linear combination, convert the result into a probability value through a logical function, and then classify according to a set threshold (usually 0.5). KNN can be used for both classification and regression. KNN classifies by measuring the distance between different feature values. The idea of ​​KNN is very simple: for any n-dimensional input vector, each corresponds to a point in the feature space, and the output is the category label or predicted value corresponding to the feature vector.

[0043] In some embodiments, the target prediction model is determined among the multiple prediction models based on the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data corresponding to each prediction model, including: for each prediction model, determining the error value of the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data, and determining the total error of the prediction model based on the error values ​​corresponding to multiple historical impact system structure data; among the multiple prediction models, determining the prediction model corresponding to the minimum total error as the target prediction model.

[0044] In this embodiment, when the prediction ability of the prediction model is stronger, the prediction error of the above prediction model is smaller. Therefore, it is necessary to determine the prediction model with the smallest prediction error as the target prediction model. For each prediction model, first, determine the error value of the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data, and then determine the total error value of the above prediction model. Among multiple prediction models, the prediction model corresponding to the minimum total error is determined as the target prediction model. Through specific numerical comparison, the purpose of accurately screening out the target prediction model is achieved. It should be noted that the average error of each prediction model can also be calculated. The average error is obtained by dividing the total error by the number of multiple errors, and the prediction model corresponding to the minimum average error is determined as the target prediction model.

[0045] In some embodiments, determining the error value between the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data includes: for each historical impact system structure data, calculating the absolute value of the difference between the standard impact acceleration and the historical impact acceleration, and determining the absolute value of the difference as the error value.

[0046] In this embodiment, for each historical impact system structure data, the smaller the difference between the standard impact acceleration and the historical impact acceleration, the smaller the error value. Therefore, the absolute value of the difference between the standard impact acceleration and the historical impact acceleration is calculated, and the difference between the two impact accelerations is reflected by the absolute value of the difference, which is the error value. The determination of the error value is converted into the calculation of a numerical value, so as to achieve the purpose of accurately determining the error value.

[0047] As shown in Table 2, Table 2 shows the error value of each prediction model at each predetermined frequency.

[0048] Table 2 Error value table of each prediction model at each predetermined frequency

[0049]

[0050] In some embodiments, determining the total error of the prediction model based on the error values ​​corresponding to the plurality of historical impact system structure data includes: calculating a sum of the plurality of error values, and determining the sum as the total error.

[0051] In this embodiment, the prediction model corresponds to multiple historical impact system structure data. Therefore, when determining the total error of the prediction model, the error values ​​corresponding to the multiple historical impact system structure data need to be considered. The total error can be obtained by calculating the sum of the multiple error values. The determination of the total error is converted into the calculation of the numerical value to achieve the purpose of accurately determining the total error.

[0052] In some embodiments, before inputting the shock system structure data corresponding to each predetermined frequency into a predetermined target prediction model, the method includes: preprocessing the shock system structure data.

[0053] In this embodiment, the impact system structure data may have low data quality. In order to improve the processing efficiency of the target prediction model on the impact system structure data, the impact system structure data is preprocessed before inputting the impact system structure data into the target prediction model to ensure the reliability of the impact system structure data.

[0054] In some embodiments, the preprocessing includes missing value filling processing and outlier removal processing.

[0055] In this embodiment, null values ​​or missing values ​​may distort the statistical analysis results and lead to deviations in the training of the machine learning model. Therefore, preprocessing includes missing value supplementation processing. By analyzing the nature and pattern of the data and removing those data that are useless for data analysis, the size of the input data set can be reduced. Therefore, preprocessing also includes outlier removal processing.

[0056] Detect missing values ​​and outliers for the impact system structure data, and supplement the missing values ​​with the average value: In the formula, is the null value corresponding to column J, is the value corresponding to the Jth column and the i-th row.

[0057] The outliers of the impact system structure data are judged by the 3Q criterion, and the upper and lower points of the outliers are obtained respectively:

[0058] Upper=μ+3σ,

[0059] Lower=μ-3σ,

[0060] Where Upper is the upper point, Lower is the lower point, μ is the mean of each feature column, and σ is the standard value of each feature column.

[0061] Values ​​exceeding the upper and lower sites were considered outliers and replaced with the upper and lower sites, respectively.

[0062] In another embodiment provided in the present application, Figure 4 As shown, the shock system structure data is collected and sorted, and the shock system structure data is input into a predetermined shock response spectrum prediction model, wherein the shock response prediction spectrum type is CatBoost, XGBoost, LightGBM, RF, DT, LR or KNN algorithm, and the prediction result is output through the shock response spectrum prediction model, and the prediction result is the target shock acceleration. Through the correspondence between the target shock acceleration and the predetermined frequency, a frequency-shock acceleration spectrum is generated, and the above spectrum type is compared with the standard spectrum type to determine whether the prediction accuracy of the target shock acceleration meets the standard. If it meets the standard, the above spectrum type is displayed. If it does not meet the standard, the input shock system structure data is readjusted. Figure 5 As shown, the specific target impact acceleration can be statistically distributed (hit rate) using error percentage intervals of ±10%, ±15%, ±20%, ±30%, etc.

[0063] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0064] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0065] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a device for determining an impact test spectrum.

[0066] refer to Figure 6 , the device for determining the impact test spectrum type comprises:

[0067] The acquisition module 10 is configured to acquire impact system structure data corresponding to a plurality of predetermined frequencies.

[0068] The output module 20 is configured to input the impact system structure data corresponding to each predetermined frequency into a predetermined target prediction model, and output the target impact acceleration corresponding to the impact system structure data through the target prediction model, wherein the target prediction model is obtained by screening from multiple pre-built prediction models.

[0069] The generating module 30 is configured to generate a frequency-shock acceleration map based on the plurality of predetermined frequencies and the target shock acceleration corresponding to the shock system structure data of the plurality of predetermined frequencies.

[0070] Through the above device, the impact system structure data corresponding to multiple predetermined frequencies are obtained. For each impact system structure data corresponding to a predetermined frequency, the impact system structure data is input into a predetermined target prediction model, and the target impact acceleration corresponding to the impact system structure data is output through the target prediction model, wherein the target prediction model is obtained by screening from multiple pre-built prediction models, thereby improving the efficiency of determining the target impact acceleration and ensuring the accuracy of determining the target impact acceleration. Based on the multiple predetermined frequencies and the target impact acceleration corresponding to the impact system structure data of the multiple predetermined frequencies, a frequency-impact acceleration spectrum is generated, and the generated frequency-impact acceleration spectrum is efficient and accurate.

[0071] In some embodiments, the output module 20 is further configured to obtain the historical impact system structure data corresponding to the multiple predetermined frequencies and the standard impact acceleration corresponding to each historical impact system structure data; for each prediction model, based on the historical impact system structure data corresponding to each predetermined frequency, determine the historical impact acceleration corresponding to each historical impact system structure data through the prediction model; based on the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data corresponding to each prediction model, determine the target prediction model among multiple prediction models.

[0072] In some embodiments, the output module 20 is also configured to determine, for each prediction model, the error value between the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data, and determine the total error of the prediction model based on the error values ​​corresponding to multiple historical impact system structure data; among the multiple prediction models, the prediction model corresponding to the minimum total error is determined as the target prediction model.

[0073] In some embodiments, the output module 20 is further configured to calculate the absolute value of the difference between the standard impact acceleration and the historical impact acceleration for each historical impact system structure data, and determine the absolute value of the difference as the error value.

[0074] In some embodiments, the output module 20 is further configured to calculate a sum of multiple error values ​​and determine the sum as the total error.

[0075] In some embodiments, a preprocessing module is further included, and the preprocessing module is configured to preprocess the shock system structure data corresponding to each predetermined frequency before inputting the shock system structure data into a predetermined target prediction model.

[0076] In some embodiments, the preprocessing module is further configured so that the preprocessing includes missing value supplementation processing and outlier removal processing.

[0077] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0078] The device of the above embodiment is used to implement the corresponding method for determining the impact test spectrum in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0079] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for determining the impact test spectrum as described in any of the above embodiments is implemented.

[0080] Figure 7 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0081] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0082] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0083] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0084] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0085] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0086] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0087] The electronic device of the above embodiment is used to implement the corresponding method for determining the impact test spectrum in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0088] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method for determining the impact test spectrum as described in any of the above embodiments.

[0089] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0090] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the method for determining the impact test spectrum as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0091] Based on the same concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer executes the method for determining the impact test spectrum as described in any of the above embodiments, which has the beneficial effects of the corresponding method embodiments and will not be repeated here.

[0092] It should be noted that the embodiments of the present application can be further described in the following manner:

[0093] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0094] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0095] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0096] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0097] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0098] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0099] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0100] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the protection scope of the present application.

Claims

1. A method for determining an impact test spectrum, characterized in that: include: Acquire impact system structure data corresponding to a plurality of predetermined frequencies; For each impact system structure data corresponding to a predetermined frequency, the impact system structure data is input into a predetermined target prediction model, and a target impact acceleration corresponding to the impact system structure data is output through the target prediction model, wherein the target prediction model is obtained by screening from a plurality of pre-built prediction models; A frequency-shock acceleration map is generated based on the plurality of predetermined frequencies and target shock accelerations corresponding to the shock system structure data of the plurality of predetermined frequencies.

2. The method according to claim 1, characterized in that: The target prediction model is obtained by screening from a plurality of pre-built prediction models, including: Acquire historical shock system structure data corresponding to the plurality of predetermined frequencies and standard shock acceleration corresponding to each historical shock system structure data; For each prediction model, based on the historical shock system structure data corresponding to each predetermined frequency, the historical shock acceleration corresponding to each historical shock system structure data is determined by the prediction model; The target prediction model is determined among the multiple prediction models based on the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data corresponding to each prediction model.

3. The method according to claim 2, characterized in that The step of determining the target prediction model from the plurality of prediction models based on the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data corresponding to each prediction model comprises: For each prediction model, determining the error value between the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data, and determining the total error of the prediction model based on the error values ​​corresponding to the multiple historical impact system structure data; Among the multiple prediction models, the prediction model corresponding to the minimum total error is determined as the target prediction model.

4. The method according to claim 3, characterized in that The step of determining the error value between the standard impact acceleration and the historical impact acceleration corresponding to each historical impact system structure data comprises: For each historical shock system structure data, the absolute value of the difference between the standard shock acceleration and the historical shock acceleration is calculated, and the absolute value of the difference is determined as the error value.

5. The method according to claim 3, characterized in that: The determining the total error of the prediction model based on the error values ​​corresponding to the plurality of historical impact system structure data comprises: A sum value of the plurality of error values ​​is calculated, and the sum value is determined as the total error.

6. The method according to claim 1, characterized in that Before inputting the shock system structure data corresponding to each predetermined frequency into a predetermined target prediction model, the method includes: The impact system structure data is preprocessed.

7. The method according to claim 6, characterized in that The preprocessing includes missing value supplementation and outlier removal.

8. A device for determining an impact test spectrum, characterized in that: include: An acquisition module is configured to acquire impact system structure data corresponding to a plurality of predetermined frequencies; an output module, configured to input the shock system structure data corresponding to each predetermined frequency into a predetermined target prediction model, and output a target shock acceleration corresponding to the shock system structure data through the target prediction model, wherein the target prediction model is obtained by screening from a plurality of pre-built prediction models; The generating module is configured to generate a frequency-shock acceleration map based on the plurality of predetermined frequencies and target shock accelerations corresponding to the shock system structure data of the plurality of predetermined frequencies.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images